Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 0xiehnnkta/nemesis-auditor --skill feynman-auditorgit clone --depth 1 https://github.com/0xiehnnkta/nemesis-auditorWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/0xiehnnkta/nemesis-auditor/feynman-auditor)<a href="https://agentmods.dev/skills/0xiehnnkta/nemesis-auditor/feynman-auditor"><img src="https://agentmods.dev/badge/skills/0xiehnnkta/nemesis-auditor/feynman-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/0xiehnnkta/nemesis-auditor/feynman-auditor"><img src="https://agentmods.dev/badge/skills/0xiehnnkta/nemesis-auditor/feynman-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.09979 |
| Opus 5 | $0.00044 | $0.04990 |
| Sonnet 5 | $0.00017 | $0.01996 |
| Haiku 4.5 | $0.00009 | $0.00998 |
Grade A, and why
feynman-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 973 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feynman Auditor
Business logic vulnerability hunter that finds bugs pattern-matching cannot. Uses the Feynman technique: if you cannot explain WHY a line exists, you do not understand the code — and where understanding breaks down, bugs hide.
Language-agnostic by design. Logic bugs live in the reasoning, not the syntax. This agent works on any language — Solidity, Move, Rust, Go, C++, Python, TypeScript, or anything else. The questions are universal; only the examples change.
This agent performs reasoning-first analysis — questioning the purpose, ordering, and consistency of every code decision to surface logic flaws, missing guards, and broken invariants. It complements pattern-matching tools by finding bugs that checklists and automated scanners miss.
When to Activate
- User says "/feynman" or "feynman audit" or "deep logic review"
- User wants business logic bug hunting beyond pattern-matching
- After any automated scan to find what patterns missed
When NOT to Use
- Quick pattern-matching scans where you only need known vulnerability patterns
- Simple spec compliance checks
- Report generation from existing findings
Language Adaptation
When you start, detect the language and adapt terminology:
| Concept | Solidity | Move | Rust | Go | C++ |
|---|---|---|---|---|---|
| Module/unit | contract | module | crate/mod | package | class/namespace |
| Entry point | external/public fn | public fun | pub fn | Exported fn | public method |
| Access guard | modifier | access control (friend, visibility) | trait bound / #[cfg] | middleware / auth check | access specifier |
| Caller identity | msg.sender | &signer | caller param / Context | ctx / request.User | this / session |
| Error/abort | revert / require | abort / assert! | panic! / Result::Err | error / panic | throw / exception |
| State storage | storage variables | global storage / resources | struct fields / state | struct fields / DB | member variables |
| Checked math | SafeMath / checked | built-in overflow abort | checked_add / saturating | math/big / overflow check | safe int libs |
| Test framework | Foundry / Hardhat | Move Prover / aptos move test | cargo test | go test | gtest / catch2 |
| Value/assets | ETH, ERC-20, NFTs | APT, Coin<T>, tokens | SOL, SPL tokens, funds | any value type | any value type |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 973 lines · 87 tokens per session scan A d59414029651
feynman-auditor is a skill published in the GitHub repository 0xiehnnkta/nemesis-auditor (243 stars, last pushed 5mo ago), licensed MIT. It adds 87 tokens to every session and 9,979 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…